Study O · Sessions & memory
Printing the position on every node does not rescue stateless sessions
Positional views
Study Overview
The Rescue Attempt
Study M's stateless failures were all placement edits, so Study O annotated every view child with its true 1-based position (plus a prompt line mapping ordinals to anchors) and re-ran the 2×2 of history × positions.
The Rescue Failed
The rescue failed: stateless accuracy moved 3–1 / 1–0 vs plain stateless (n.s.), and sessions ending byte-perfect stayed at 15/20 vs full history's 19/20; models misplaced nodes that had the correct position printed on them.
Not Arithmetic
Whatever history contributes to placement, it is not arithmetic. Positions with history were descriptively the best cells in the whole series (gemini: 20/20 end-states, 60/60 late placements) but not significantly better than history alone: harmless, possibly mildly helpful, not a substitute for memory. (Study P, next chart, found the actual substitute.)